Dipl.-Ing. Dr. Andreas Mayr, MSc

Science Park 3 - Floor 3 - Room 327
+43 732 2468 4528
+43 732 2468 4539
mayr(at)ml.jku.at

Personal data/education

MSc in Computer Science and Bioinformatics from Johannes Kepler University Linz, Austria
PhD of Natural Sciences in Computer Science, Johannes Kepler University Linz, Austria

Research topics

Deep Neural Networks
Theoretical Properties of DNNs
Cheminformatics
Deep Learning for Physics
Graph Networks

Selected Publications

Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter: Boundary Graph Neural Networks for 3D Simulations, 2023 https://arxiv.org/abs/2106.11299, opens an external URL in a new window
accepted for an oral talk in the technical program at the Thirty-Seventh AAAI Conference on Artificial Intelligence (AAAI-23)
Official Proceedings not yet available
Code: https://github.com/ml-jku/bgnn, opens an external URL in a new window
Data: https://ml.jku.at/research/bgnn/download/, opens an external URL in a new window
Andreas Mayr, Sebastian Lehner, Arno Mayrhofer, Christoph Kloss, Sepp Hochreiter, Johannes Brandstetter: Learning 3D Granular Flow Simulations, 2021 https://arxiv.org/abs/2105.01636, opens an external URL in a new window
accepted at Deep Learning for Simulation (SimDL) Workshop @ ICLR 2021 (https://simdl.github.io/schedule/, opens an external URL in a new window)
Poster: https://simdl.github.io/posters/42-supp_poster.pdf, opens an external URL in a new window
Contributed Talk: https://slideslive.de/38955315/learning-3d-granular-flow-simulations?ref=speaker-10792-latest, opens an external URL in a new window
Noé Sturm, Andreas Mayr, Thanh Le Van, Vladimir Chupakhin, Hugo Ceulemans, Joerg Wegner, Jose-Felipe Golib-Dzib, Nina Jeliazkova, Yves Vandriessche, Stanislav Böhm, Vojtech Cima, Jan Martinovic, Nigel Greene, Tom Vander Aa, Thomas J. Ashby, Sepp Hochreiter, Ola Engkvist, Günter Klambauer, Hongming Chen: Industry-scale application and evaluation of deep learning for drug target prediction, Journal of Cheminformatics, 2020 https://doi.org/10.1186/s13321-020-00428-5, opens an external URL in a new window
Thomas Adler, Johannes Brandstetter, Michael Widrich, Andreas Mayr, David Kreil, Michael Kopp, Günter Klambauer, Sepp Hochreiter: Cross-Domain Few-Shot Learing by Representation Fusion, 2020 https://arxiv.org/abs/2010.06498, opens an external URL in a new window
Andreas Mayr, Günter Klambauer, Thomas Unterthiner, Marvin Steijaert, Jörg K. Wegner, Hugo Ceulemans, Djork-Arne Clevert, Sepp Hochreiter: Large-scale comparison of machine learning methods for drug target prediction on ChEMBL, opens an external URL in a new window, Chemical Science, 2018
Günter Klambauer, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter: Self-Normalizing Neural Networks, opens an external URL in a new window, Advances in Neural Information Processing Systems 30 (NIPS), 2017
Michael Treml, José Arjona-Medina, Thomas Unterthiner, Rupesh Durgesh, Felix Friedmann, Peter Schuberth, Andreas Mayr, Martin Heusel, Markus Hofmarcher, Michael Widrich, Bernhard Nessler, Sepp Hochreiter Speeding up Semantic Segmentation for Autonomous Driving, opens an external URL in a new window, Machine Learning for Intelligent Transportation Systems, in conjunction with Neural Information Processing Systems (NIPS), 2016
Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Sepp Hochreiter: Deep Learning for Drug Target Prediction, GPU Technology Conference Europe (GTC Europe), 2016,
Best Poster Award
Andreas Mayr, Günter Klambauer, Thomas Unterthiner, Sepp Hochreiter: DeepTox: Toxicity Prediction using Deep Learning, opens an external URL in a new window Frontiers in Environmental Science, 2016
Federica Eduati, Lara M Mangravite, Tao Wang, Hao Tang, ... , Sepp Hochreiter, Günter Klambauer, Andreas Mayr, ... , Ivan Rusyn, Fred A Wright, Gustavo Stolovitzky, Yang Xie, Julio Saez-Rodriguez: Prediction of human population responses to toxic compounds by a collaborative competition, opens an external URL in a new window Nature Biotechnology, Advance online publication, 2015
Günter Klambauer, Martin Wischenbart, Michael Mahr, Thomas Unterthiner, Andreas Mayr, Sepp Hochreiter: Rchemcpp: a web service for structural analoging in ChEMBL, Drugbank and the Connectivity Map, opens an external URL in a new window Bioinformatics, 2015
Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Sepp Hochreiter: Toxicity Prediction using Deep Learning, opens an external URL in a new window, arXiv pre-print, 2015
Djork-Arne Clevert, Thomas Unterthiner, Andreas Mayr, Hubert Ramsauer, Sepp Hochreiter:Rectified Factor Networks, opens an external URL in a new window arXiv pre-print, 2015
Thomas Unterthiner, Andreas Mayr, Günter Klambauer, Marvin Steijaert, Jörg Wegner, Hugo Ceulemans, Sepp Hochreiter: Deep Learning as an Opportunity in Virtual Screening, opens an external URL in a new window,Deep Learning and Representation Learning Workshop, in conjunction with Neural Information Processing Systems (NIPS 2014), Montreal, Canada, 2014
Marc Streit, Samuel Gratzl, Michael Gillhofer, Andreas Mayr, Andreas Mitterecker, Sepp Hochreiter: Furby: fuzzy force-directed bicluster visualization, opens an external URL in a new window BMC Bioinformatics, 2014
Djork-Arne Clevert, Andreas Mayr, Andreas Mitterecker, Günter Klambauer, Armand Valsesia, Karl Forner, Marianne Tuefferd, Willem Talloen, Jerome Wojcik, Hinrich Göhlmann, Sepp Hochreiter Increasing the discovery power of -omics studies, opens an external URL in a new window Systems Biomedicine, 2013
Günter Klambauer, Karin Schwarzbauer, Andreas Mayr, Djork-Arne Clevert, Andreas Mitterecker, Ulrich Bodenhofer, Sepp Hochreiter cn.MOPS: mixture of Poissons for discovering copy number variations in next generation sequencing data with a low false discovery rate, opens an external URL in a new window, Nucl. Acids Res., 2012
Djork-Arne Clevert, Andreas Mitterecker, Andreas Mayr, Günter Klambauer, Marianne Tuefferd, An De Bondt, Willem Talloen, Hinrich Göhlmann, Sepp Hochreiter: cn.FARMS: a latent variable model to detect copy number variations in microarray data with a low false discovery rate, opens an external URL in a new window, Nucl. Acids Res., 2011
Sepp Hochreiter, Ulrich Bodenhofer, Martin Heusel, Andreas Mayr, Andreas Mitterecker, Adetayo Kasim, Tatsiana Khamiakova, Suzy Van Sanden, Dan Lin, Willem Talloen, Luc Bijnens, Hinrich H.W. Göhlmann, Ziv Shkedy, Djork-Arne Clevert: FABIA: Factor Analysis for Bicluster Acquisition, opens an external URL in a new window, Bioinformatics, 2010

Teaching

Exercises in Theoretical Concepts of Machine Learning
Exercises in Machine Learning: Unsupervised Techniques
Exercises in Bioinformatics (for students of Biological Chemistry)
Exercises Bioinformatics II: Theoretical Bioinformatics and Machine Learning

Name	Purpose	Lifetime	Provider
CookieConsent	This cookie saves your settings about cookie-handling at this website.	1 year	JKU
se_mode	This cookie is used for settings of the site search.	1 year	JKU

Name	Purpose	Lifetime	Provider
_gcl_au	This cookie is used by Google Analytics to understand user interaction with the website.	3 months	Google
_ga	This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors.	2 years	Google
_gid	This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the website is doing. The data collected including the number visitors, the source where they have come from, and the pages visited in an anonymous form.	1 day	Google
_gat_UA-112203476-1	This is a pattern type cookie set by Google Analytics, where the pattern element on the name contains the unique identity number of the account or website it relates to. It appears to be a variation of the _gat cookie which is used to limit the amount of data recorded by Google on high traffic volume websites.	1 minute	Google
_pk_id	This cookie is used to store a few details about the user such as the unique visitor ID.	13 months	JKU
_pk_ses	This cookie is a short lived cookie used to temporarily store data for the visit.	30 minutes	JKU
_pk_ref	This cookie is used to store the attribution information, the referrer initially used to visit the website.	6 months	JKU

Name	Purpose	Lifetime	Provider
_gcl_au	This cookie is used by Google Analytics to understand user interaction with the website.	3 months	Google
_ga	This cookie is installed by Google Analytics. The cookie is used to calculate visitor, session, campaign data and keep track of site usage for the site's analytics report. The cookies store information anonymously and assign a randomly generated number to identify unique visitors.	2 years	Google
_gid	This cookie is installed by Google Analytics. The cookie is used to store information of how visitors use a website and helps in creating an analytics report of how the website is doing. The data collected including the number visitors, the source where they have come from, and the pages visited in an anonymous form.	1 day	Google
_gac_UA-112203476-1	Contains campaign related information for the user and measures the AdWords campaign success.	90 days	Google
test_cookie	This cookie is set to determine if the website visitor's browser supports cookies. Doesn't contain personal identifier.	15 minutes	Google
IDE	This cookie carries out information about how the end user uses the website and any advertising that the end user may have seen before visiting the said website.	1 year	Google
_gcl_aw	This cookie is set when a user clicks an ad to reach our website. It informs about the success of campaigns and allows to connect ads to conversion targets.	3 months	Google
AMCV_xx	This is a pattern type cookie name associated with Adobe Marketing Cloud. It stores a unique visitor identifier, and uses an organisation identifier to allow a company to track users across their domains and services.	3 years	LinkedIn
bcookie	Contains a browser ID.	2 years	LinkedIn
bscookie	Contains a browser ID for a secure connection.	2 years	LinkedIn
lang	This cookie is used to store the language preference of our visitors	Session	LinkedIn
lidc	This cookie carries out information about how the end user uses the website and any advertising that the end user may have seen before visiting the said website.	1 day	LinkedIn
lissc	This cookie is used to analyze how a visitor interacts with embedded services.	1 year	LinkedIn
UserMatchHistory	This cookie is set when a user clicks an ad to reach our website. It informs about the success of campaigns and allows to connect ads to conversion targets.	30 days	LinkedIn
fr	This cookie is set when a user clicks an ad to reach our website. It informs about the success of campaigns and allows to connect ads to conversion targets.	90 days	Facebook
fbp	This cookie is used to display advertisings, for example third-party real time offers.	90 days	Facebook
sc_at	This cookie is used to identify a visitor across multiple domains.	1 year	Snap
sc-country	This cookie is used to determine a visitor's country.	1 day	Snap
uid	This cookie sets a random User-ID and helps at real time bidding for display advertising to targeted audiences.	60 days	Adform
C	This cookie identifies if user’s browser accepts cookies. 1 – Cookies are allowed, 3 – Opt-out.	30 days	Adform

Dipl.-Ing. Dr. Andreas Mayr, MSc

{{ dict().Publications }}

{{ typ[0].TYP }}

{{ dict().Lectures }}

{{ typ[0].TYP }}

{{ dict().ResearchProjects }}

{{ typ[0].TYP }}

{{ dict().Scs }}

{{ typ[0].TYP }}

{{ dict().Innovations }}

{{ typ[0].TYP }}

Personal data/education

Research topics

Selected Publications

Teaching